import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model_id = "Qwen/Qwen3-VL-8B"

tokenizer = AutoTokenizer.from_pretrained(
    "YOUR_USERNAME/qwen3vl-skinCAP-4bit-lora",
    trust_remote_code=True
)

base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    device_map="auto",
    load_in_4bit=True,
    trust_remote_code=True
)

model = PeftModel.from_pretrained(
    base_model,
    "aravind2599/qwen3vl-skinCAP-4bit-lora"
)

Framework versions

PEFT 0.18.0